Cassava cultivation is important to the nation because of the products and raw materials that are supplied to industries. However, Its cultivation is affected by diseases such as cassava brown leaf and cassava mosaic, which have been classified using a Support Vector Machine (SVM). SqueezeNet pretrained Convolutional Neural Network (SPCNN) is adjudged a very effective image detection and classification algorithm with limited usage areas. This research, therefore was used to detect and classify cassava leaf diseases using SPCNN and SPCNN with multiclass SVM. Performance evaluation of both techniques showed that SPCNN effectively detected and classified cassava leaf diseases with optimal accuracies of 92.22% and 98.89% for SPCNN and SPCNN-SVM, respectively. Keywords- SqueezeNet, SVM, Cassava diseases, Feature extraction, Transfer learning Arinola I. O., Oke O. A. & Falohun A. S. (2026): Detection and Classification of Cassava Leaf Diseases using Squeezenet Pretrained Convolutional Neural Network and Support Vector Machine. Journal of Advances in Mathematical & Computational Science. Vol. 14, No. 1. Pp 1-12 Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V14N1P1

Tracking student attendance in universities remains an essential but often inefficient task, especially in developing nations where records are still kept manually on paper. This work designs and evaluates a web-based Automated Attendance Monitoring System (AAMS) that integrates fingerprint biometrics with matriculation numbers for student identification. This work ensures that attendance records are accurate and reliable. Which will encourage students to attend lectures regularly, thereby leading to improvement in their academic performance. The AAMS replaces manual procedures with a transparent digital workflow, improving reliability and reducing administrative overhead. Unified Modeling Language (UML) diagrams guided the system design, while implementation was carried out using MySQL, PHP, HTML, JavaScript, and CSS. Manual method and biometric attendance approaches, when compared, showed that biometric authentication reduces impersonation and absenteeism, also improves student accountability. Overall, the findings suggest that a web-based Automated Attendance Monitoring System (AAMS) can help to improve students’ academic performance and gives the institutions a reliable approach to monitor attendance and performance. Keywords: Lecture Participation, Identity Number, Attendance, Biometric, Fingerprint Recognition, Performance, Automated Attendance CISDI Journal Reference Format Egejuru Shama Chidi, Nosike Paul & Egejuru Ngozi Chidozie (2025): A Biometric Identity-Enabled Automated Attendance Monitoring System for Tracking Lecture Attendance and Performance. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 16 No 4, Pp 61-80. Available online at www.isteams.net/cisdijournal. dx.doi.org/10.22624/AIMS/CISDI/V16N4P6

The alarming rise in kidnapping incidents across Nigeria demands innovative, reliable, and context-appropriate personal safety solutions. Existing GSM panic buttons and mobile applications are often hindered by hardware constraints, dependence on constant internet connectivity, and slow activation under duress. This paper presents the design and implementation of an anti-kidnapping system that integrates an ESP8266-based emergency button with an Android mobile application, enabling dual-mode alert delivery via Internet or SMS. When the emergency button is pressed, the ESP8266 powers on and instantly enters Wi-Fi Access Point (AP) mode. The Android application, running a foreground service, connects as a client, acquires GPS coordinates from the phone, and combines them with a timestamp and the user’s preconfigured emergency contacts. This information is sent to an IoT server, which triggers notifications via Firebase Cloud Messaging. If internet connectivity is unavailable, the application automatically switches to SMS mode to ensure alert delivery. Hardware-triggered activation and firmware-controlled power-down ensure zero standby power consumption, enabling extended operational readiness on a single charge. Field tests across varying connectivity conditions showed activation in less than 2 seconds, alert delivery in 5–9 s depending on connectivity, and GPS accuracy typically within ±10 m. The system’s low cost, portability, and independence from continuous network access make it suitable for deployment across Nigeria’s urban, rural, and low-resource settings, with potential for broader emergency response applications. Keywords: Anti-Kidnapping Technology, Emergency Alert System, GPS, SMS, Internet-of-Things, Mobile Application

Anomaly detection is essential in applications such as financial fraud detection, network security, and system health monitoring. This study presents a hybrid anomaly detection model for financial transactions, combining the strengths of both unsupervised and supervised learning techniques—Isolation Forest and Random Forest, respectively. the Isolation Forest algorithm, performs unsupervised detection of outliers, effectively identifying rare or irregular data points without requiring labeled input. The detected anomalies are then used to construct a pseudo-labeled dataset, which is subsequently used to train a Random Forest classifier. The Random Forest model learns discriminative patterns between normal and anomalous data, enhancing overall detection capabilities. The system is implemented in Python using Scikit-learn for model development and evaluation. Experiments on benchmark financial transaction "Credit Card Fraud Detection Dataset from Kaggle" The hybrid model achieved a precision of 99.7%, recall of near 100%, and an F1-score of 99.98%, outperforming standalone algorithm The model also improved robustness to noise and better scalability for large datasets. Keywords: Anomaly Detection, Financial Fraud, Hybrid Machine Learning, Supervised Learning, Security, Unsupervised Learning. CISDI Journal Reference Format Azubuike Nnendah Daisy; Anireh, Vincent Ike-Emeka & Sako, D.J.S. (2025): A Model for Anomaly Detection in Financial Transactions using Hybrid Machine Learning Technique. Computing, Information Systems, Development Informatics and Allied Research Journal. Vol 16 No 3, Pp 37-50 Available online at www.isteams.net/cisdijournal. dx.doi.org/10.22624/AIMS/CISDI/V16N3P3

Women’s entrepreneurship is increasingly recognised as a catalyst for economic growth and sustainable development; however, indigenous women in Nigeria continue to encounter entrenched socio-cultural, financial, legal, educational, and technological barriers that hinder business success. This conceptual paper aims to critically analyse these constraints and propose a context-sensitive framework for sustainable empowerment. Drawing on an extensive review of peer-reviewed journal articles, policy reports, and development agency publications published between 2000 and 2024, the study synthesises existing knowledge through the lens of institutional theory and the gender-and-development framework. Key barriers identified include gender stereotyping, restricted access to finance, complex regulatory requirements, limited entrepreneurial and digital literacy, and inadequate representation in formal networks. The paper advances a Sustainable Empowerment Framework that integrates financial inclusion strategies, targeted education and training, social capital strengthening, and gender-responsive policy reforms. Emphasis is placed on mentorship programs, cooperative societies, and digital empowerment as mechanisms to bridge structural gaps. The findings underscore the potential of leveraging cultural norms for empowerment through community engagement and collaborative interventions involving government agencies, non-governmental organisations, financial institutions, and traditional leaders. By aligning cultural transformation with inclusive economic growth, this paper offers actionable recommendations for policymakers, scholars, and development practitioners seeking to enhance the resilience and competitiveness of indigenous women entrepreneurs in Nigeria. Keywords: Indigenous Women, Entrepreneurship, Cultural Norms, Empowerment, Nigeria Journal Reference Format: Ojogbo, L.U & Odor, H.O. (2025): Cultural Norms and the Empowerment of Indigenous Women Entrepreneurs in Nigeria: Toward a Sustainable Framework. Social Informatics, Business, Politics, Law, Environmental Sciences & Technology Journal. Vol. 11, No. 2. Pp 67-78. www.isteams/socialinformaticsjournal. dx.doi.org/10.22624/AIMS/SIJ/V11N2P5

Most Latin word and character recognition systems have numerous classification algorithms to automate the identification of handwritten characters. However, despite extensive research on various Latin-based languages, relatively limited attention has been given to the recognition of handwritten text in Nigerian indigenous languages. Handwritten character recognition is challenging due to the variations in shape and style. In addition to that, these characters naturally vary among individuals. This work presents an offline character recognition system for Igbo handwritten alphabets using convolutional neural networks. In this study, a dataset comprising 9,000 character images was created, with 250 distinct samples for each of the 36 letters in the Igbo alphabet. Of these, 200 samples per character (a total of 7,200 images) were pre-processed, binarized, and normalized for training two Convolutional Neural Network (CNN) models. The remaining 50 samples per character (1,800 images) were reserved for testing. Model 1 and Model 2 achieved recognition accuracies of 83.5% and 85.0%, respectively. The proposed approach demonstrates potential for enhancing the automation and digitization of handwritten Igbo texts into machine-readable formats. Keywords: Optical Character Recognition, Igbo Handwritten Characters, Nigerian, Indigenous, Convolutional Neural Network Journal Reference Format: Woods, N.C. & Oyedeji, O.A. (2025): Offline Handwritten Character Recognition for Igbo Alphabets Using Convolutional Neural Networks. Journal of Behavioural Informatics, Digital Humanities and Development Rese Vol. 11 No. 2. Pp 115-126 https://www.isteams.net/behavioralinformaticsjournal dx.doi.org/10.22624/AIMS/BHI/V11N2P11

Access control systems play a critical role in maintaining data integrity and confidentiality. Utilizing biometric recognition improves security by utilizing distinct behavioral and physiological characteristics. This study aims to address issues of accuracy and computing efficiency by creating a sophisticated access control system with iris-based biometrics and a novel fusion of Chicken Swarm Optimization (CSO) and Self-Organizing Feature Maps (SOFM). Iris images were acquired, preprocessed, and subjected to feature extraction via Log-Gabor filters to highlight critical attributes. The CSO algorithm optimized the SOFM's learning parameters, resulting in an improved clustering and recognition process. Comparative analysis against the standard SOFM demonstrated significant enhancements in sensitivity (96.09%), specificity (90.59%), precision (96.85%), and accuracy (94.72%). Additionally, processing time was reduced, ensuring feasibility for real-time applications. These results establish the Modified CSO-SOFM as a robust and efficient method for biometric access control. Future efforts will focus on incorporating multimodal biometrics and advanced optimization strategies to further elevate system performance. Keywords: Enhanced Self-Organizing Feature Map, Iris-Based Access Control System, Biometrics CISDI Journal Reference Format Jeremiah Y.S., Ojo O. J., Adigun E. B. & Ogunkan S. K. (2025): Development Of An Enhanced Self-Organizing Feature Map Iris-Based Access Control System. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 16 No 1, Pp 35-44. Available online at www.isteams.net/cisdijournal. dx.doi.org/10.22624/AIMS/CISDI/V16N1P5